• Title/Summary/Keyword: 2 단계(Type II) 교차효율성 메트릭스 군집모형

Search Result 1, Processing Time 0.019 seconds

A Study on the Asia Container Ports Clustering Using Hierarchical Clustering(Single, Complete, Average, Centroid Linkages) Methods with Empirical Verification of Clustering Using the Silhouette Method and the Second Stage(Type II) Cross-Efficiency Matrix Clustering Model (계층적 군집분석(최단, 최장, 평균, 중앙연결)방법에 의한 아시아 컨테이너 항만의 클러스터링 측정 및 실루엣방법과 2단계(Type II) 교차효율성 메트릭스 군집모형을 이용한 실증적 검증에 관한 연구)

  • Park, Ro-Kyung
    • Journal of Korea Port Economic Association
    • /
    • v.37 no.1
    • /
    • pp.31-70
    • /
    • 2021
  • The purpose of this paper is to measure the clustering change and analyze empirical results, and choose the clustering ports for Busan, Incheon, and Gwangyang ports by using Hierarchical clustering(single, complete, average, and centroid), Silhouette, and 2SCE[the Second Stage(Type II) cross-efficiency] matrix clustering models on Asian container ports over the period 2009-2018. The models have chosen number of cranes, depth, birth length, and total area as inputs and container TEU as output. The main empirical results are as follows. First, ranking order according to the efficiency increasing ratio during the 10 years analysis shows Silhouette(0.4052 up), Hierarchical clustering(0.3097 up), and 2SCE(0.1057 up). Second, according to empirical verification of the Silhouette and 2SCE models, 3 Korean ports should be clustered with ports like Busan Port[ Dubai, Hong Kong, and Tanjung Priok], and Incheon Port and Gwangyang Port are required to cluster with most ports. Third, in terms of the ASEAN, it would be good to cluster like Busan (Singapore), Incheon Port (Tanjung Priok, Tanjung Perak, Manila, Tanjung Pelpas, Leam Chanbang, and Bangkok), and Gwangyang Port(Tanjung Priok, Tanjung Perak, Port Kang, Tanjung Pelpas, Leam Chanbang, and Bangkok). Third, Wilcoxon's signed-ranks test of models shows that all P values are significant at an average level of 0.852. It means that the average efficiency figures and ranking orders of the models are matched each other. The policy implication is that port policy makers and port operation managers should select benchmarking ports by introducing the models used in this study into the clustering of ports, compare and analyze the port development and operation plans of their ports, and introduce and implement the parts which required benchmarking quickly.